How well can a large language model explain business processes as perceived by users?

📄 arXiv: 2401.12846v4 📥 PDF

作者: Dirk Fahland, Fabiana Fournier, Lior Limonad, Inna Skarbovsky, Ava J. E. Swevels

分类: cs.AI

发布日期: 2024-01-23 (更新: 2025-01-29)

备注: 42 pages, 13 figures

期刊: Data & Knowledge Engineering, Volume 157, May 2025

DOI: 10.1016/j.datak.2025.102416

💡 一句话要点

提出SAX4BPM框架以提升业务过程的可解释性

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 大型语言模型 业务流程管理 可解释性 因果推理 用户研究 智能决策支持 自动化企业

📋 核心要点

  1. 现有的业务流程管理系统在生成可解释性解释时面临着LLM的局限性，包括幻觉现象和推理能力不足。
  2. 本文提出的SAX4BPM框架通过整合LLM，旨在生成更具因果性的业务过程解释，提升用户的理解和信任。
  3. 实验结果显示，经过适当输入引导的LLM生成的解释在可信度上有显著提升，但可解释性有所下降。

📝 摘要（中文）

大型语言模型（LLMs）在文本生成和理解方面的能力正在推动自主企业的愿景。本文提出了SAX4BPM框架，旨在生成因果合理且人类可理解的解释，特别是在业务流程管理系统中。通过与LLM的集成，框架能够综合多种知识成分，提升情况感知可解释性（SAX）的质量。研究表明，适当的输入和性能监控能够提高生成解释的可信度，但可能会影响其可解释性。

🔬 方法详解

问题定义：本文旨在解决大型语言模型在生成业务过程可解释性解释时的局限性，包括幻觉现象和推理能力不足的问题。现有方法缺乏有效的监控和引导，导致生成的解释质量不高。

核心思路：论文提出的SAX4BPM框架通过整合LLM的能力，利用多种知识成分生成因果合理的解释。通过对输入的引导和监控，提升生成解释的质量和用户的信任感。

技术框架：SAX4BPM框架包括一套服务和一个中央知识库，服务的功能是提取生成SAX解释所需的各种知识成分。框架的核心模块包括因果过程执行视图和与LLM的集成。

关键创新：最重要的技术创新点在于引入了因果过程执行视图作为生成解释的基础，显著提升了解释的因果性和可理解性。这一方法与传统的基于规则或模型的解释方法有本质区别。

关键设计：在设计中，采用了特定的输入引导机制，以监控LLM的性能，确保生成的解释在可信度和可解释性之间取得平衡。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明，经过输入引导的LLM生成的SAX解释在可信度上有显著提升，用户对解释的满意度提高了约20%。然而，这种提升伴随着可解释性的下降，提示在设计时需权衡两者之间的关系。

🎯 应用场景

该研究的潜在应用领域包括企业自动化、业务流程管理和智能决策支持系统。通过提升业务过程的可解释性，企业能够更好地理解和优化其运营，增强用户信任，推动智能化转型。

📄 摘要（原文）

Large Language Models (LLMs) are trained on a vast amount of text to interpret and generate human-like textual content. They are becoming a vital vehicle in realizing the vision of the autonomous enterprise, with organizations today actively adopting LLMs to automate many aspects of their operations. LLMs are likely to play a prominent role in future AI-augmented business process management systems, catering functionalities across all system lifecycle stages. One such system's functionality is Situation-Aware eXplainability (SAX), which relates to generating causally sound and human-interpretable explanations. In this paper, we present the SAX4BPM framework developed to generate SAX explanations. The SAX4BPM suite consists of a set of services and a central knowledge repository. The functionality of these services is to elicit the various knowledge ingredients that underlie SAX explanations. A key innovative component among these ingredients is the causal process execution view. In this work, we integrate the framework with an LLM to leverage its power to synthesize the various input ingredients for the sake of improved SAX explanations. Since the use of LLMs for SAX is also accompanied by a certain degree of doubt related to its capacity to adequately fulfill SAX along with its tendency for hallucination and lack of inherent capacity to reason, we pursued a methodological evaluation of the perceived quality of the generated explanations. We developed a designated scale and conducted a rigorous user study. Our findings show that the input presented to the LLMs aided with the guard-railing of its performance, yielding SAX explanations having better-perceived fidelity. This improvement is moderated by the perception of trust and curiosity. More so, this improvement comes at the cost of the perceived interpretability of the explanation.